bboylyg/BackdoorLLM

This repository provides a benchmark for prompt injection attacks and defenses in LLMs

An easy-to-use Python framework to generate adversarial jailbreak prompts.

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

Agent Security Bench (ASB)

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

A survey on harmful fine-tuning attack for large language model (ACM CSUR)

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

New ways of breaking app-integrated LLMs